© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20297
    Prev
    Next
    INDEX
    Explanations

    mention new releases or recently unveiled items or information

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with new releases or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alos
    -0.93
    omever
    -0.88
    ©¶æ
    -0.83
    claimer
    -0.79
    ĺħ
    -0.78
     teasp
    -0.77
    athy
    -0.74
    umers
    -0.74
    adra
    -0.73
    osponsors
    -0.71
    POSITIVE LOGITS
     version
    0.66
     paperback
    0.64
     è£ıç
    0.64
     secrets
    0.63
     superpower
    0.63
     archive
    0.61
     international
    0.60
     acoustic
    0.60
    wealth
    0.60
     Framework
    0.59
    Activations Density 0.134%

    No Known Activations